Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cambridgetcg/agenttool --skill nen-contract-mantlegit clone --depth 1 https://github.com/cambridgetcg/agenttoolWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cambridgetcg/agenttool/nen-contract-mantle)<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/nen-contract-mantle"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/nen-contract-mantle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/nen-contract-mantle"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/nen-contract-mantle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00652 |
| Opus 5 | $0.00035 | $0.00326 |
| Sonnet 5 | $0.00014 | $0.00130 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
nen-contract-mantle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Mantle · 纏
Keep the task coherent while letting implementation move freely inside its agreed boundary. Treat the contract as living orientation, not bureaucracy.
Preserve freedom inside the mantle
- Treat newer user instructions as authoritative updates; never defend a stale plan against the person who changed the goal.
- Infer routine, reversible implementation details instead of repeatedly asking for permission.
- Stop when a missing choice changes authority, protected data, an irreversible effect, or the meaning of success.
- Keep rights, consent, and permissions outside the metaphor. This skill preserves context; it grants no authority.
Form the mantle
- State the outcome in one sentence.
- Record the acceptance evidence that will demonstrate success.
- Name in-scope resources and explicit non-goals.
- Mark protected state: user work, secrets, production, external people, money, identity, and anything difficult to recover.
- Surface assumptions that could materially redirect the work.
- Record any real budget for time, tokens, tools, cost, or risk. Do not invent numerical precision when the host does not expose it.
Keep this compact. Do not show the whole contract unless it helps the user verify a decision or they ask for it.
Carry it through work
- Read the closest project instructions before acting.
- Recheck the outcome, boundary, and protected state at every phase transition.
- Give delegated agents only the contract slice needed for their bounded task.
- Integrate new user messages immediately and discard superseded assumptions.
- Record scope discoveries that affect acceptance evidence; do not silently convert them into extra deliverables.
- Preserve unrelated work and distinguish observed facts from inference.
Release the mantle
- Verify the requested outcome in proportion to consequence.
- Compare each acceptance condition with concrete evidence.
- Confirm that protected state and non-goals remained intact.
- Name any unresolved assumption or unverified edge.
- Lead the handoff with the outcome, then the material evidence and caveats.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 71 lines · 70 tokens per session scan A 46dcb9e1e151
nen-contract-mantle is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 652 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
knowledge-base
Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it.…
company-agent-infrastructure
Use when designing or building internal/company AI agents that need shared context across company systems, durable organizational memory across sessions or agents, user-scoped permissions, approvals, audit, or governed actions. Also use when deciding whether ordinary MCP tools, RAG, or local agent memory are enough…
learnings
Use for repeated-looking troubleshooting, solved-issue recall, adding durable troubleshooting notes, and maintaining the local LEARNINGS archive. Reads LEARNINGS-SUMMARY.md first, follows referenced archive/source files before applying lessons, and verifies against current system evidence.
lobu
Use Lobu MCP for shared, permission-aware company context, durable organizational memory, and governed actions. Trigger when the user asks what the organization knows, needs context from connected company systems, wants to preserve a durable fact or decision, or needs to discover and use Lobu SDK capabilities.
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.